少标签节点图上的结构感知共识网络
Structure-Aware Consensus Network on Graphs with Few Labeled Nodes
AI总结:
针对少标签图节点分类,本文提出单分支结构感知共识网络SACn,通过强增强视图共识、结构信息整合和类别感知伪标签选择提升未标注数据利用,并在三个基准上取得优于现有方法的结果。
摘要:
由于监督信号有限,仅有少量已标注节点的图节点分类面临重大挑战。传统方法通常以直推式学习方式利用图,无法有效利用丰富的未标注数据以及图中固有的结构信息。为解决这些问题,我们从三个方面提出结构感知共识网络(SACn)。首先,SACn在两个强增强视图之间采用新颖的结构感知共识学习策略,该策略能够充分挖掘未标注节点的潜在有用信息以及整个图的结构信息。其次,SACn独特地整合图的结构信息以实现强强共识学习,在保持多视图学习的同时提高未标注数据的利用率。第三,与基于双分支图神经网络的方法不同,SACn被设计为在单分支架构内进行多视图特征学习。此外,类别感知伪标签选择策略有助于解决类别不平衡问题,并实现有效的弱到强监督。在三个基准数据集上的大量实验表明,SACn在节点分类任务中表现优越,尤其是在极低标签率下,其性能优于最先进方法,同时保持计算简洁。源代码可在 https://github.com/kunzhan/SACn 获取。
英文摘要:
Graph node classification with few labeled nodes presents significant challenges due to limited supervision. Conventional methods often exploit the graph in a transductive learning manner. They fail to effectively utilize the abundant unlabeled data and the structural information inherent in graphs. To address these issues, we introduce a Structure-Aware Consensus Network (SACN) from three perspectives. Firstly, SACN leverages a novel structure-aware consensus learning strategy between two strongly augmented views. The proposed strategy can fully exploit the potentially useful information of the unlabeled nodes and the structural information of the entire graph. Secondly, SACN uniquely integrates the graph's structural information to achieve strong-to-strong consensus learning, improving the utilization of unlabeled data while maintaining multiview learning. Thirdly, unlike two-branch graph neural network-based methods, SACN is designed for multiview feature learning within a single-branch architecture. Furthermore, a class-aware pseudolabel selection strategy helps address class imbalance and achieve effective weak-to-strong supervision. Extensive experiments on three benchmark datasets demonstrate SACN's superior performance in node classification tasks, particularly at very low label rates, outperforming state-of-the-art methods while maintaining computational simplicity.The source code is available at https://github.com/kunzhan/SACN
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。